debian/patches/remove-autoupdate-mechanism.patch: Refresh.

[youtubedl] / youtube_dl / extractor / kuwo.py

diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py
index 1077846f296150c8503dbe091a0a096df4620719..63e10125e670b96cf706bb6c1c131ea33377a920 100644 (file)
--- a/youtube_dl/extractor/kuwo.py
+++ b/youtube_dl/extractor/kuwo.py
@@ -2,13 +2,14 @@
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re

-import itertools

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

+from ..compat import compat_urlparse

 from ..utils import (
     get_element_by_id,
     clean_html,
     ExtractorError,
 from ..utils import (
     get_element_by_id,
     clean_html,
     ExtractorError,

+    InAdvancePagedList,

     remove_start,
 )
 
     remove_start,
 )
 


@@ -23,14 +24,26 @@ class KuwoBaseIE(InfoExtractor):
         {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10}
     ]
 
         {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10}
     ]
 

-    def _get_formats(self, song_id):
+    def _get_formats(self, song_id, tolerate_ip_deny=False):

         formats = []
         for file_format in self._FORMATS:
         formats = []
         for file_format in self._FORMATS:

+            query = {
+                'format': file_format['ext'],
+                'br': file_format.get('br', ''),
+                'rid': 'MUSIC_%s' % song_id,
+                'type': 'convert_url',
+                'response': 'url'
+            }
+

             song_url = self._download_webpage(
             song_url = self._download_webpage(

-                'http://antiserver.kuwo.cn/anti.s?format=%s&br=%s&rid=MUSIC_%s&type=convert_url&response=url' %
-                (file_format['ext'], file_format.get('br', ''), song_id),
+                'http://antiserver.kuwo.cn/anti.s',

                 song_id, note='Download %s url info' % file_format['format'],
                 song_id, note='Download %s url info' % file_format['format'],

+                query=query, headers=self.geo_verification_headers(),

             )
             )

+
+            if song_url == 'IPDeny' and not tolerate_ip_deny:
+                raise ExtractorError('This song is blocked in this region', expected=True)
+

             if song_url.startswith('http://') or song_url.startswith('https://'):
                 formats.append({
                     'url': song_url,
             if song_url.startswith('http://') or song_url.startswith('https://'):
                 formats.append({
                     'url': song_url,


@@ -39,14 +52,14 @@ class KuwoBaseIE(InfoExtractor):
                     'preference': file_format['preference'],
                     'abr': file_format.get('abr'),
                 })
                     'preference': file_format['preference'],
                     'abr': file_format.get('abr'),
                 })

-        self._sort_formats(formats)
+

         return formats
 
 
 class KuwoIE(KuwoBaseIE):
     IE_NAME = 'kuwo:song'
     IE_DESC = '酷我音乐'
         return formats
 
 
 class KuwoIE(KuwoBaseIE):
     IE_NAME = 'kuwo:song'
     IE_DESC = '酷我音乐'

-    _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>\d+?)/'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P<id>\d+)'

     _TESTS = [{
         'url': 'http://www.kuwo.cn/yinyue/635632/',
         'info_dict': {
     _TESTS = [{
         'url': 'http://www.kuwo.cn/yinyue/635632/',
         'info_dict': {


@@ -57,39 +70,47 @@ class KuwoIE(KuwoBaseIE):
             'upload_date': '20080122',
             'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
         },
             'upload_date': '20080122',
             'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c'
         },

+        'skip': 'this song has been offline because of copyright issues',

     }, {
         'url': 'http://www.kuwo.cn/yinyue/6446136/',
         'info_dict': {
             'id': '6446136',
             'ext': 'mp3',
             'title': '心',
     }, {
         'url': 'http://www.kuwo.cn/yinyue/6446136/',
         'info_dict': {
             'id': '6446136',
             'ext': 'mp3',
             'title': '心',

+            'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c',

             'creator': 'IU',
             'upload_date': '20150518',
         },
         'params': {
             'creator': 'IU',
             'upload_date': '20150518',
         },
         'params': {

-            'format': 'mp3-320'
+            'format': 'mp3-320',

         },
         },

+    }, {
+        'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
+        'only_matching': True,

     }]
 
     def _real_extract(self, url):
         song_id = self._match_id(url)
     }]
 
     def _real_extract(self, url):
         song_id = self._match_id(url)

-        webpage = self._download_webpage(
+        webpage, urlh = self._download_webpage_handle(

             url, song_id, note='Download song detail info',
             errnote='Unable to get song detail info')
             url, song_id, note='Download song detail info',
             errnote='Unable to get song detail info')

+        if song_id not in urlh.geturl() or '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage:
+            raise ExtractorError('this song has been offline because of copyright issues', expected=True)

 
         song_name = self._html_search_regex(
 
         song_name = self._html_search_regex(

-            r'<h1[^>]+title="([^"]+)">', webpage, 'song name')
-        singer_name = self._html_search_regex(
-            r'<div[^>]+class="s_img">\s*<a[^>]+title="([^>]+)"',
-            webpage, 'singer name', fatal=False)
+            r'<p[^>]+id="lrcName">([^<]+)</p>', webpage, 'song name')
+        singer_name = remove_start(self._html_search_regex(
+            r'<a[^>]+href="http://www\.kuwo\.cn/artist/content\?name=([^"]+)">',
+            webpage, 'singer name', fatal=False), '歌手')

         lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
         if lrc_content == '暂无':     # indicates no lyrics
             lrc_content = None
 
         formats = self._get_formats(song_id)
         lrc_content = clean_html(get_element_by_id('lrcContent', webpage))
         if lrc_content == '暂无':     # indicates no lyrics
             lrc_content = None
 
         formats = self._get_formats(song_id)

+        self._sort_formats(formats)

 
         album_id = self._html_search_regex(
 
         album_id = self._html_search_regex(

-            r'<p[^>]+class="album"[^<]+<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',
+            r'<a[^>]+href="http://www\.kuwo\.cn/album/(\d+)/"',

             webpage, 'album id', fatal=False)
 
         publish_time = None
             webpage, 'album id', fatal=False)
 
         publish_time = None


@@ -118,13 +139,13 @@ class KuwoIE(KuwoBaseIE):
 class KuwoAlbumIE(InfoExtractor):
     IE_NAME = 'kuwo:album'
     IE_DESC = '酷我音乐 - 专辑'
 class KuwoAlbumIE(InfoExtractor):
     IE_NAME = 'kuwo:album'
     IE_DESC = '酷我音乐 - 专辑'

-    _VALID_URL = r'http://www\.kuwo\.cn/album/(?P<id>\d+?)/'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P<id>\d+?)/'

     _TEST = {
         'url': 'http://www.kuwo.cn/album/502294/',
         'info_dict': {
             'id': '502294',
     _TEST = {
         'url': 'http://www.kuwo.cn/album/502294/',
         'info_dict': {
             'id': '502294',

-            'title': 'M',
-            'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c',
+            'title': 'Made\xa0Series\xa0《M》',
+            'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f',

         },
         'playlist_count': 2,
     }
         },
         'playlist_count': 2,
     }


@@ -154,15 +175,13 @@ class KuwoAlbumIE(InfoExtractor):
 class KuwoChartIE(InfoExtractor):
     IE_NAME = 'kuwo:chart'
     IE_DESC = '酷我音乐 - 排行榜'
 class KuwoChartIE(InfoExtractor):
     IE_NAME = 'kuwo:chart'
     IE_DESC = '酷我音乐 - 排行榜'

-    _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'
+    _VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P<id>[^.]+).htm'

     _TEST = {
         'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
         'info_dict': {
             'id': '香港中文龙虎榜',
     _TEST = {
         'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
         'info_dict': {
             'id': '香港中文龙虎榜',

-            'title': '香港中文龙虎榜',
-            'description': 're:\d{4}第\d{2}期',

         },
         },

-        'playlist_mincount': 10,
+        'playlist_mincount': 7,

     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):


@@ -171,30 +190,24 @@ class KuwoChartIE(InfoExtractor):
             url, chart_id, note='Download chart info',
             errnote='Unable to get chart info')
 
             url, chart_id, note='Download chart info',
             errnote='Unable to get chart info')
 

-        chart_name = self._html_search_regex(
-            r'<h1[^>]+class="unDis">([^<]+)</h1>', webpage, 'chart name')
-
-        chart_desc = self._html_search_regex(
-            r'<p[^>]+class="tabDef">(\d{4}第\d{2}期)</p>', webpage, 'chart desc')
-

         entries = [
             self.url_result(song_url, 'Kuwo') for song_url in re.findall(
         entries = [
             self.url_result(song_url, 'Kuwo') for song_url in re.findall(

-                r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/"', webpage)
+                r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage)

         ]
         ]

-        return self.playlist_result(entries, chart_id, chart_name, chart_desc)
+        return self.playlist_result(entries, chart_id)

 
 
 class KuwoSingerIE(InfoExtractor):
     IE_NAME = 'kuwo:singer'
     IE_DESC = '酷我音乐 - 歌手'
 
 
 class KuwoSingerIE(InfoExtractor):
     IE_NAME = 'kuwo:singer'
     IE_DESC = '酷我音乐 - 歌手'

-    _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P<id>[^/]+)'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P<id>[^/]+)'

     _TESTS = [{
         'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
         'info_dict': {
             'id': 'bruno+mars',
     _TESTS = [{
         'url': 'http://www.kuwo.cn/mingxing/bruno+mars/',
         'info_dict': {
             'id': 'bruno+mars',

-            'title': 'Bruno Mars',
+            'title': 'Bruno\xa0Mars',

         },
         },

-        'playlist_count': 10,
+        'playlist_mincount': 329,

     }, {
         'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
         'info_dict': {
     }, {
         'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
         'info_dict': {


@@ -202,8 +215,11 @@ class KuwoSingerIE(InfoExtractor):
             'title': 'Ali',
         },
         'playlist_mincount': 95,
             'title': 'Ali',
         },
         'playlist_mincount': 95,

+        'skip': 'Regularly stalls travis build',  # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540

     }]
 
     }]
 

+    PAGE_SIZE = 15
+

     def _real_extract(self, url):
         singer_id = self._match_id(url)
         webpage = self._download_webpage(
     def _real_extract(self, url):
         singer_id = self._match_id(url)
         webpage = self._download_webpage(


@@ -211,25 +227,29 @@ class KuwoSingerIE(InfoExtractor):
             errnote='Unable to get singer info')
 
         singer_name = self._html_search_regex(
             errnote='Unable to get singer info')
 
         singer_name = self._html_search_regex(

-            r'<div class="title clearfix">\s*<h1>([^<]+)<span', webpage, 'singer name'
-        )
+            r'<h1>([^<]+)</h1>', webpage, 'singer name')

 
 

-        entries = []
-        first_page_only = False if re.search(r'/music(?:_\d+)?\.htm', url) else True
-        for page_num in itertools.count(1):
-            webpage = self._download_webpage(
-                'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num),
-                singer_id, note='Download song list page #%d' % page_num,
-                errnote='Unable to get song list page #%d' % page_num)
+        artist_id = self._html_search_regex(
+            r'data-artistid="(\d+)"', webpage, 'artist id')
+
+        page_count = int(self._html_search_regex(
+            r'data-page="(\d+)"', webpage, 'page count'))

 
 

-            entries.extend([
-                self.url_result(song_url, 'Kuwo') for song_url in re.findall(
-                    r'<p[^>]+class="m_name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/',
+        def page_func(page_num):
+            webpage = self._download_webpage(
+                'http://www.kuwo.cn/artist/contentMusicsAjax',
+                singer_id, note='Download song list page #%d' % (page_num + 1),
+                errnote='Unable to get song list page #%d' % (page_num + 1),
+                query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})
+
+            return [
+                self.url_result(compat_urlparse.urljoin(url, song_url), 'Kuwo')
+                for song_url in re.findall(
+                    r'<div[^>]+class="name"><a[^>]+href="(/yinyue/\d+)',

                     webpage)
                     webpage)

-            ][:10 if first_page_only else None])
+            ]

 
 

-            if first_page_only or not re.search(r'<a[^>]+href="[^"]+">下一页</a>', webpage):
-                break
+        entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE)

 
         return self.playlist_result(entries, singer_id, singer_name)
 
 
         return self.playlist_result(entries, singer_id, singer_name)
 


@@ -237,7 +257,7 @@ class KuwoSingerIE(InfoExtractor):
 class KuwoCategoryIE(InfoExtractor):
     IE_NAME = 'kuwo:category'
     IE_DESC = '酷我音乐 - 分类'
 class KuwoCategoryIE(InfoExtractor):
     IE_NAME = 'kuwo:category'
     IE_DESC = '酷我音乐 - 分类'

-    _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'
+    _VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P<id>\d+?).htm'

     _TEST = {
         'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
         'info_dict': {
     _TEST = {
         'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm',
         'info_dict': {


@@ -245,7 +265,7 @@ class KuwoCategoryIE(InfoExtractor):
             'title': '八十年代精选',
             'description': '这些都是属于八十年代的回忆！',
         },
             'title': '八十年代精选',
             'description': '这些都是属于八十年代的回忆！',
         },

-        'playlist_count': 30,
+        'playlist_mincount': 24,

     }
 
     def _real_extract(self, url):
     }
 
     def _real_extract(self, url):


@@ -260,6 +280,8 @@ class KuwoCategoryIE(InfoExtractor):
         category_desc = remove_start(
             get_element_by_id('intro', webpage).strip(),
             '%s简介：' % category_name)
         category_desc = remove_start(
             get_element_by_id('intro', webpage).strip(),
             '%s简介：' % category_name)

+        if category_desc == '暂无':
+            category_desc = None

 
         jsonm = self._parse_json(self._html_search_regex(
             r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)
 
         jsonm = self._parse_json(self._html_search_regex(
             r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id)


@@ -274,15 +296,21 @@ class KuwoCategoryIE(InfoExtractor):
 class KuwoMvIE(KuwoBaseIE):
     IE_NAME = 'kuwo:mv'
     IE_DESC = '酷我音乐 - MV'
 class KuwoMvIE(KuwoBaseIE):
     IE_NAME = 'kuwo:mv'
     IE_DESC = '酷我音乐 - MV'

-    _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P<id>\d+?)/'
+    _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P<id>\d+?)/'

     _TEST = {
         'url': 'http://www.kuwo.cn/mv/6480076/',
         'info_dict': {
             'id': '6480076',
     _TEST = {
         'url': 'http://www.kuwo.cn/mv/6480076/',
         'info_dict': {
             'id': '6480076',

-            'ext': 'mkv',
-            'title': '我们家MV',
+            'ext': 'mp4',
+            'title': 'My HouseMV',

             'creator': '2PM',
         },
             'creator': '2PM',
         },

+        # In this video, music URLs (anti.s) are blocked outside China and
+        # USA, while the MV URL (mvurl) is available globally, so force the MV
+        # URL for consistent results in different countries
+        'params': {
+            'format': 'mv',
+        },

     }
     _FORMATS = KuwoBaseIE._FORMATS + [
         {'format': 'mkv', 'ext': 'mkv', 'preference': 250},
     }
     _FORMATS = KuwoBaseIE._FORMATS + [
         {'format': 'mkv', 'ext': 'mkv', 'preference': 250},


@@ -304,7 +332,17 @@ class KuwoMvIE(KuwoBaseIE):
         else:
             raise ExtractorError('Unable to find song or singer names')
 
         else:
             raise ExtractorError('Unable to find song or singer names')
 

-        formats = self._get_formats(song_id)
+        formats = self._get_formats(song_id, tolerate_ip_deny=True)
+
+        mv_url = self._download_webpage(
+            'http://www.kuwo.cn/yy/st/mvurl?rid=MUSIC_%s' % song_id,
+            song_id, note='Download %s MV URL' % song_id)
+        formats.append({
+            'url': mv_url,
+            'format_id': 'mv',
+        })
+
+        self._sort_formats(formats)

 
         return {
             'id': song_id,
 
         return {
             'id': song_id,